mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
85b29990be
* adding rapidocr engine for ocr in docling Signed-off-by: swayam-singhal <swayam.singhal@inito.com> * fixing styling format Signed-off-by: Swaymaw <swaymaw@gmail.com> * updating pyproject.toml and poetry.lock to fix ci bugs Signed-off-by: Swaymaw <swaymaw@gmail.com> * help poetry pinning for python3.9 Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * simplifying rapidocr options so that device can be changed using a single option for all models Signed-off-by: Swaymaw <swaymaw@gmail.com> * fix styling issues and small bug in rapidOcrOptions Signed-off-by: Swaymaw <swaymaw@gmail.com> * use default device until we enable global management Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: swayam-singhal <swayam.singhal@inito.com> Signed-off-by: Swaymaw <swaymaw@gmail.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: swayam-singhal <swayam.singhal@inito.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import (
|
|
EasyOcrOptions,
|
|
OcrMacOptions,
|
|
PdfPipelineOptions,
|
|
RapidOcrOptions,
|
|
TesseractCliOcrOptions,
|
|
TesseractOcrOptions,
|
|
)
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
def main():
|
|
input_doc = Path("./tests/data/2206.01062.pdf")
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.do_ocr = True
|
|
pipeline_options.do_table_structure = True
|
|
pipeline_options.table_structure_options.do_cell_matching = True
|
|
|
|
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions
|
|
# ocr_options = EasyOcrOptions(force_full_page_ocr=True)
|
|
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
|
|
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
|
|
# ocr_options = RapidOcrOptions(force_full_page_ocr=True)
|
|
ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
|
|
pipeline_options.ocr_options = ocr_options
|
|
|
|
converter = DocumentConverter(
|
|
format_options={
|
|
InputFormat.PDF: PdfFormatOption(
|
|
pipeline_options=pipeline_options,
|
|
)
|
|
}
|
|
)
|
|
|
|
doc = converter.convert(input_doc).document
|
|
md = doc.export_to_markdown()
|
|
print(md)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|